© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 333
    Prev
    Next
    INDEX
    Explanations

    titles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "Gr" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.80
     quo
    -0.70
    ĸļ
    -0.66
     writ
    -0.64
     Lei
    -0.62
     capped
    -0.61
     Sands
    -0.61
    vention
    -0.61
     Mith
    -0.60
     shortened
    -0.59
    POSITIVE LOGITS
    iffin
    1.28
    umpy
    1.23
    anny
    1.21
    udge
    1.19
    ains
    1.13
    iff
    1.13
    ayson
    1.10
    ands
    1.07
    aced
    1.07
    illed
    1.06
    Activations Density 0.025%

    No Known Activations